Learning Adaptive Perturbation-Conditioned Contexts for Robust Transcriptional Response Prediction

TL;DR

AdaPert is a novel framework that models sparsity and biological structure to improve the accuracy of predicting transcriptional responses to genetic perturbations, overcoming noise and mean collapse issues.

Contribution

It introduces perturbation-specific subgraphs and adaptive learning to better separate true signals from noise in transcriptional response prediction.

Findings

Outperforms existing methods on multiple benchmarks

Achieves higher DEG-aware evaluation scores

More accurately recovers perturbation-specific changes

Abstract

Predicting high-dimensional transcriptional responses to genetic perturbations is challenging due to severe experimental noise and sparse gene-level effects. Existing methods often suffer from mean collapse, where high correlation is achieved by predicting global average expression rather than perturbation-specific responses, leading to many false positives and limited biological interpretability. Recent approaches incorporate biological knowledge graphs into perturbation models, but these graphs are typically treated as dense and static, which can propagate noise and obscure true perturbation signals. We propose AdaPert, a perturbation-conditioned framework that addresses mean collapse by explicitly modeling sparsity and biological structure. AdaPert learns perturbation-specific subgraphs from biological knowledge graphs and applies adaptive learning to separate true signals from noise. Across multiple genetic perturbation benchmarks, AdaPert consistently outperforms existing baselines and achieves substantial improvements on DEG-aware evaluation metrics, indicating more accurate recovery of perturbation-specific transcriptional changes.